ComfyUI Node
Ollama Image To Text
A ComfyUI node in 🌙DW/ImageToText with 7 inputs and 1 output.
Ollama Image To Text
- images
- description
◄queryDescribe the main content of the picture under the speed，Do not generate any descriptive text.►
◄model▾►
◄seed0►
◄top_k40►
◄max_tokens100►
◄keep_alivefalse►
Category🌙DW/ImageToText
Inputs (7)
| Name | Type | Default | Description |
|---|---|---|---|
| images | IMAGE | — | |
| query | STRING | Describe the main content of the picture under the speed，Do not generate any descriptive text. | — |
| model | COMBO | 1 options: No models found | |
| seed | INT | 00–18446744073709550000 | — |
| top_k | FLOAT | 400–100 | — |
| max_tokens | INT | 1001–1024 | — |
| keep_alive | BOOLEAN | false | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| description | STRING | — |